Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     gef
    0.49
     أكثر
    0.47
     أول
    0.44
     Misch
    0.44
    সঙ্ঘ
    0.43
    يم
    0.43
     minimax
    0.43
    慝
    0.42
     Reviewed
    0.42
    ينات
    0.42
    POSITIVE LOGITS
    ne
    0.52
    ua
    0.47
    ds
    0.47
    aua
    0.47
    datasets
    0.45
    dds
    0.43
    decision
    0.43
    kami
    0.43
    du
    0.42
    sobre
    0.42
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.